Triple

T2784820
Position Surface form Disambiguated ID Type / Status
Subject Unilever E61784 entity
Predicate hasBrand P1500 FINISHED
Object Cif
Cif is a household cleaning product brand known for its creams and sprays used to remove tough dirt and stains from various surfaces.
 E297565 NE FINISHED

How this triple was built (4 steps)

Every LLM step that produced this triple, in pipeline order — named-entity classification, the disambiguation choices (the exact options shown, with the pick highlighted), and the generated description. The batch + timestamp of each is in the Provenance table below.

NER Named-entity recognition gpt-5-mini
Instruction
Given a phrase, classify it is english named entity (e.g., persons, organizations, works of art) in Latin script, or not (e.g., literals, dates, URLs, verbose phrases). For disambiguation, the statement where the phrase occurs as object is also given. Please return a JSON object with `phrase` (string, the phrase being analyzed) and `is_ne` (boolean, indicating whether the phrase is a Named Entity).
Input
Phrase: Cif | Statement: [Unilever, hasBrand, Cif]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Cif
Context triple: [Unilever, hasBrand, Cif]
  • A. Cito
    Cito is a former Major League Baseball outfielder and manager best known for leading the Toronto Blue Jays to back-to-back World Series championships in 1992 and 1993.
  • B. CIEF
    CIEF is the abbreviated name for the Canton Fair, China’s largest and oldest comprehensive trade exhibition held biannually in Guangzhou.
  • C. CFC
    CFC is a leading Canadian institution dedicated to advancing the careers of filmmakers, screenwriters, and other media creators through professional training and development programs.
  • D. CFC
    CFC is the commonly used abbreviation for the United States Court of Federal Claims, a federal court that hears monetary claims against the U.S. government.
  • E. CFC
    CFC is the abbreviation commonly used for the Combined Forces Command, a joint military headquarters coordinating combined operations.
  • F. None of above. chosen
  • G. Unsure - the case is ambiguous/there is not enough information to decide.
NEDg Description generation gpt-5.1
Instruction
Generate a one-sentence description of the target entity. 
You are given a context triple in the form (subject, predicate, object), where the object is the target entity. 
# Instructions
Use the triple to infer relevant information about the entity. Describe the entity based on what is most defining, well-known. 
Avoid repeating the information from the triple, unless really essential.
# Response Format
Return only the sentence: "Description: [one-sentence description of the target entity]"
Input
Entity: Cif
Triple: [Unilever, hasBrand, Cif]
Generated description
Cif is a household cleaning product brand known for its creams and sprays used to remove tough dirt and stains from various surfaces.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Cif
Target entity description: Cif is a household cleaning product brand known for its creams and sprays used to remove tough dirt and stains from various surfaces.
  • A. Cito
    Cito is a former Major League Baseball outfielder and manager best known for leading the Toronto Blue Jays to back-to-back World Series championships in 1992 and 1993.
  • B. CIEF
    CIEF is the abbreviated name for the Canton Fair, China’s largest and oldest comprehensive trade exhibition held biannually in Guangzhou.
  • C. CFC
    CFC is a leading Canadian institution dedicated to advancing the careers of filmmakers, screenwriters, and other media creators through professional training and development programs.
  • D. CFC
    CFC is the commonly used abbreviation for the United States Court of Federal Claims, a federal court that hears monetary claims against the U.S. government.
  • E. CFC
    CFC is the abbreviation commonly used for the Combined Forces Command, a joint military headquarters coordinating combined operations.
  • F. None of above. chosen

Provenance (5 batches)

The batch behind each pipeline step, in order, with when it ran. Timestamps are batch-level — stages were processed in waves, so the object chain (NER → NED1 → NEDg → NED2) reads in order, but predicate / elicitation batches can sit in a different wave.

Step Stage Batch ID Status When
creating Elicitation batch_69ab4b7e43c48190997b8fc8fb1663ab completed March 6, 2026, 9:47 p.m.
NER Named-entity recognition batch_69abddaf223c8190959bb0b336e5b7c0 completed March 7, 2026, 8:11 a.m.
NED1 Entity disambiguation (via context triple) batch_69afc0629e8c81909b55d9838e681ba2 completed March 10, 2026, 6:55 a.m.
NEDg Description generation batch_69afc15513f48190a22f83571be2e0bd completed March 10, 2026, 6:59 a.m.
NED2 Entity disambiguation (via description) batch_69afc1c9440c8190abf9dc063109af45 completed March 10, 2026, 7:01 a.m.
Created at: March 6, 2026, 9:57 p.m.